%0 Conference Proceedings
%T Identifying Potentially Cancerous Tissues in Chromoendoscopy Images
%A Farhan Riaz
%A Fernando Vilariño
%A Mario Dinis-Ribeiro
%A Miguel Coimbraln
%E J. Vitria, J.M. Sanches
%B 5th Iberian Conference on Pattern Recognition and Image Analysis
%D 2011
%V 6669
%I Springer
%C Berlin
%@ 978-3-642-21256-7
%F Farhan Riaz2011
%O MV;SIAI
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=1726), last updated on Fri, 14 Mar 2014 16:02:57 +0100
%X The dynamics of image acquisition conditions for gastroenterology imaging scenarios pose novel challenges for automatic computer assisted decision systems. Such systems should have the ability to mimic the tissue characterization of the physicians. In this paper, our objective is to compare some feature extraction methods to classify a Chromoendoscopy image into two different classes: Normal and Potentially cancerous. Results show that LoG filters generally give best classification accuracy among the other feature extraction methods considered.
%K Endoscopy
%K Computer Assisted Diagnosis
%K Gradient.
%U http://refbase.cvc.uab.es/files/RVD2011.pdf
%U http://dx.doi.org/10.1007/978-3-642-21257-4_88
%P 709-716